Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

10-2024

Abstract

Deep Learning Systems (DLSs) have been widely applied in safety-critical tasks such as autopilot. However, when a perturbed input is fed into a DLS for inference, the DLS often has incorrect outputs (i.e., faults). DLS testing techniques (e.g., DeepXplore) detect such faults by generating perturbed inputs to explore data flows that induce faults. Since a DLS often has infinitely many data flows, existing techniques require developers to manually specify a set of activation values in a DLS’s neurons for exploring fault-inducing data flows. Unfortunately, recent studies show that such manual effort is tedious and can detect only a tiny proportion of fault-inducing data flows. In this paper, we present Themis, the first automatic DLS testing system, which attains strong fault detection capability by ensuring a full coverage of fault-inducing data flows at a high probability. Themis carries a new workflow for automatically and systematically revealing data flows whose internal neurons’ outputs vary substantially when the inputs are slightly perturbed, as these data flows are likely fault-inducing. We evaluated Themis on ten different DLSs and found that on average the number of faults detected by Themis was 3.78X more than four notable DLS testing techniques. By retraining all evaluated DLSs with the detected faults, Themis also increased (regained) these DLSs’ accuracies on average 14.7X higher than all baselines.

Keywords

Deep Learning Systems (DLSs), Safety-critical tasks, Autopilot, Fault detection, Perturbed input, DLS testing techniques, Data flows

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Data Science and Engineering; Information Systems and Management

Publication

Proceeding of the 35th International Symposium on Software Reliability Engineering, Tsukuba, Japan, 2024 October 28-31

Identifier

10.48550/arXiv.2405.09314

Publisher

IEEE

City or Country

New Jersey

Additional URL

https://doi.org/10.48550/arXiv.2405.09314

Share

COinS